-
Notifications
You must be signed in to change notification settings - Fork 639
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
TypeError: unsupported operand type(s) for /: 'NoneType' and 'float' #243
Comments
|
Got:
|
@andriy-onufriyenko Did you specify the image extension correctly? I can replicate your error by passing |
@andriy-onufriyenko, |
Renamed the files. Changed the path. Nothing helped.
|
@andriy-onufriyenko, I've created a PR #249 to address your issue. You could use this branch to test it for now. I've used the following configuration, and successfully trained the model. dataset:
name: Concrete_Crack #options: [mvtec, btech, folder, concrete_crack]
format: folder # mvtec
path: ./datasets/Concrete_Crack/ # ./datasets/MVTec
normal_dir: "train/Negative"
abnormal_dir: "test/Positive"
normal_test_dir: "test/Negative"
task: segmentation
mask: ./datasets/Concrete_Crack/ground_truth/Positive
extensions: ".jpg"
split_ratio: 0.1
seed: 0
image_size: 227
train_batch_size: 8 # 16
test_batch_size: 8 # 16
inference_batch_size: 8 # 16
fiber_batch_size: 64
num_workers: 8
transform_config:
train: null
val: null
create_validation_set: false
tiling:
apply: false
tile_size: null
stride: null
remove_border_count: 0
use_random_tiling: False
random_tile_count: 16 |
The same problem with you. |
@haobo827 if you use the above branch until it's merged, it should work. |
|
@andriy-onufriyenko, unfortunately, I'm unable to reproduce this issue. Could you perhaps try the mvtec format? Anyone else having this issue? Any tips to reproduce? |
@andriy-onufriyenko, I'm closing this issue since The issue you're having now is due to setting |
Hi, i 'm dealing with the same error after i change dataset: Error:
Epoch 0: 28%|██▊ | 28/99 [00:04<00:10, 6.62it/s, loss=nan] |
This error occurs when the masks cannot be read properly. Make sure you provided the right paths for the mask. |
I want to train CFLOW model on custom dataset.
config.yaml
My dataset have the same structure like MVTec
![image](https://user-images.githubusercontent.com/103642699/164267180-6ffd544c-78c5-452d-a034-ab3f60237869.png)
To Reproduce
python3 tools/train.py --model_config_path anomalib/models/cflow/config.yaml
When I start the training, I get an error:
The text was updated successfully, but these errors were encountered: